Cognitive System Semantic Relationship Extraction for Predictive Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing semantic relationship extraction methods are limited by their reliance on pre-defined entities, leading to information loss and inefficiency in making complex predictions, as they fail to utilize relationships between entities and non-entities effectively.
Innovation Solution
A cognitive data processing system that extracts and processes both defined and undefined entities and non-entities to determine semantic relationships, allowing for the identification of relationships between entities and non-entities, thereby enhancing predictive analytics capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If entity-based semantic relationship extraction is used, then the structure and organization of relationships are improved, but information loss occurs because non-entity phrases are excluded
Solution Approach 1:
The patent extends the traditional entity-based semantic network by adding a new dimension that incorporates non-entity phrases. This transforms the system from handling only entity-to-entity relationships to managing entity-to-non-entity, non-entity-to-entity, and non-entity-to-non-entity relationships, thereby capturing previously excluded information while maintaining structural organization
Solution Approach 2:
The semantic relationship extraction system is enhanced to perform multiple functions: it continues to extract entity-based relationships while simultaneously capturing non-entity phrases and their contextual meanings. This multi-functional approach allows the system to process both structured entity data and unstructured phrase data within a unified framework
2Device complexity
If only entity-to-entity relationships are analyzed, then the complexity of the system is reduced, but the ability to make complex predictions is limited
Solution Approach 1:
The patent segments the semantic relationship extraction process into distinct components: entity identification, non-entity phrase extraction, relationship determination, and prediction generation. This segmentation allows the system to manage complexity through modular processing while comprehensively analyzing all relationship types for improved prediction accuracy
3Speed
If pre-defined entities are used for semantic analysis, then the processing speed is improved, but adaptability to new concepts is reduced
Solution Approach 1:
The system dynamically adapts between using pre-defined entities for efficient processing and extracting new non-entity phrases for novel concepts. By making the semantic network dynamic and flexible, the system can quickly process known entities while simultaneously discovering and incorporating new concepts, thereby maintaining both speed and adaptability
Data Source
AI summary
According to embodiments of the present invention, methods, systems and computer readable media are provided, in a cognitive data processing system, for implementing a predictive analytics system that utilizes entity and non-entity information. A collection of content is processed to extract defined entities pertaining to one or more domains. Semantic relationships are determined between objects within the collection of content, wherein the objects include undefined entities. The defined entities and objects are resolved based on entity definitions and the semantic relationships to determine defined entities and undefined entities for a resulting data set. The resulting data set is processed to identify one or more relationships between a defined entity and an undefined entity.